hai
cloudyu
AI & ML interests
Personal contributor
m2 ultra 192G
QQ 206 887 187
Organizations
cloudyu's activity
How can I use this great model in python script?
1
#1 opened 5 days ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
example code doesn't work at all
7
#2 opened 11 days ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
how to use these great models in python scripts?
1
#1 opened 10 days ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Update README.md with license information
#4 opened 12 days ago
by
Chen-01AI
Update README.md with license information
#15 opened 12 days ago
by
Chen-01AI
Update README.md with license information
#6 opened 12 days ago
by
Chen-01AI
Update README.md with license information
#4 opened 12 days ago
by
Chen-01AI
Update README.md with license information
#2 opened 12 days ago
by
Chen-01AI
Update README.md with license information
#17 opened 14 days ago
by
Chen-01AI
Reconvert GGUF for the MoE, due to llama.cpp update
1
#1 opened 2 months ago
by
CombinHorizon
good model
1
#1 opened about 2 months ago
by
gopi87
"status" is "FINISHED", but I cannot find the result of my model
1
#694 opened 3 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
output is not correct.
1
#7 opened 3 months ago
by
flymonk
how to run WizardLM-2-8x22B.Q4_K_S.gguf.part2of2 and part1?
3
#1 opened 3 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
can you plesse share how to make this version?
3
#3 opened 3 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
How much RAM does it need to run on Mac m1?
5
#2 opened 3 months ago
by
davideuler
MMLU is only 25.64, anything wrong?
5
#8 opened 3 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
VRAM Estimates
6
#3 opened 4 months ago
by
ernestr
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64e407a9825f4133e75aeada/Em9QI75U3eJUZUgai7Kzy.png)
From your work, I find a new way to do model ensemble
1
#14 opened 3 months ago
by
xxx1
Hardware requirement
2
#5 opened 4 months ago
by
Dtree07
Adding Evaluation Results
1
#4 opened 4 months ago
by
ac-automata
4x version
1
#15 opened 4 months ago
by
ehartford
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63111b2d88942700629f5771/u2a9y-yx6TG0N31OhMSHI.png)
Very interesting
1
#1 opened 4 months ago
by
ehartford
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63111b2d88942700629f5771/u2a9y-yx6TG0N31OhMSHI.png)
Thank you for your continued contribution to Chinese-language community|感谢你对中文社区的持续贡献
1
#1 opened 4 months ago
by
sdakfjlkfasf
Why did you take down gemma-7b-it-dpo-v1
1
#2 opened 4 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
how to run this model?
3
#1 opened 4 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Adding Evaluation Results
1
#1 opened 4 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
这个是基于中文的微调吗 效果这么好
1
#2 opened 5 months ago
by
xuan0126
Train after merging?
2
#1 opened 5 months ago
by
adi-kmt
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6523d85b27d1f3d84ab3a0a4/GF159gtSvxSWR9TAJIQby.jpeg)
how to run this model
#2 opened 5 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Upload tokenizer.model
1
#1 opened 5 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
Upload tokenizer.model
#2 opened 5 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
how to dequantised from q5 to f16?
#7 opened 5 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Update README.md
#2 opened 5 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Update README.md
#1 opened 5 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Can you make a 2.4bpw exl2 quantisation for this model?
4
#1 opened 6 months ago
by
xldistance
How did you train the gating?
10
#6 opened 6 months ago
by
osanseviero
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6032802e1f993496bc14d9e3/w6hr-DEQot4VVkoyRIBiy.png)
Unable to access cloudyu/Pluto_24B_DPO_400
1
#1 opened 6 months ago
by
umarbutler
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/RG1zarVQK8PSeCPuKVoro.jpeg)
this is really great dataset
1
#2 opened 6 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
Could you share the training script?
1
#1 opened 6 months ago
by
andysalerno
Announcement: Flagging merged models with incorrect metadata
82
#510 opened 6 months ago
by
clefourrier
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1644340617257-noauth.png)
congrat!new SOTA!
4
#1 opened 6 months ago
by
cloudyu
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64618bc5cf638aa8f856137c/zbUqrIeHjz41P3O2b3eey.jpeg)
How many GPU memories that the MoE module needs?
2
#8 opened 6 months ago
by
Jazzlee
The function_calling and translation abilities are weaker than Mixtral 8x7b
1
#11 opened 6 months ago
by
bingw5
Multi-langua?
1
#7 opened 6 months ago
by
oFDz
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/EP1UsMD4_tc9cct2EIUYh.png)
8.0bpw-h8-exl2 quant of this model
6
#1 opened 6 months ago
by
Light4Bear
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1666277867924-noauth.png)
The difference of prompt template between base models
3
#8 opened 6 months ago
by
Cartinoe5930
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63e087b6a98d931aa90c1b9c/96c6IT3f1pWGLbRdRDB2U.png)
Do you need fine-tune after merging?
3
#5 opened 6 months ago
by
tanganke
Can VLLM be used for inference acceleration?
2
#2 opened 6 months ago
by
obtion
Vram
2
#7 opened 6 months ago
by
DKRacingFan
source code and paper?
8
#6 opened 6 months ago
by
josephykwang
How does the MoE work?
3
#5 opened 6 months ago
by
PacmanIncarnate
Should not be called mixtral, the models made into the moe are yi based
9
#2 opened 6 months ago
by
teknium
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6317aade83d8d2fd903192d9/erOwgMXc_CZih3uMoyTAp.jpeg)
Problem with tokenizer
1
#4 opened 6 months ago
by
ipechman
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1666298585081-noauth.png)
One or two models during inference?
3
#3 opened 6 months ago
by
Venkman42
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6493317e9621f988db6c469c/qoxbdTDi-Pouyjq4MwiAG.png)